Skip to content
MCP server

Kurlo

Let assistants run and write the saved API requests in a Kurlo workspace

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, macOS, Windows
Runs
Locally
Version
3.1.3
Listing updated
3 days ago

About Kurlo

Kurlo is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.

Kurlo is an open source API client that keeps requests as readable YAML files, and kurlo mcp serves a workspace to an assistant over stdin and stdout. The assistant can see collections and environments, run a saved request and read the response, run a collection's tests, or send a one-off call that uses an environment's variables.

It can also write: add and change saved requests with tests, write tests from a response, save responses as examples and set environment variables. An agent adding an endpoint to your service can add its request in the same commit, and the app, if open, shows the change within a second.

One command, npx -y @kurlo/cli mcp install --env Local, adds it to Claude Code, Claude Desktop, Codex, Cursor, VS Code, Windsurf and Gemini CLI. The --read-only flag installs only tools that read and run, and --workspace picks a folder.

Install

Run in a terminal

claude mcp add kurlo -- npx -y @kurlo/cli

Add to claude_desktop_config.json

{
  "mcpServers": {
    "kurlo": {
      "command": "npx",
      "args": [
        "-y",
        "@kurlo/cli"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "kurlo": {
      "command": "npx",
      "args": [
        "-y",
        "@kurlo/cli"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "kurlo": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@kurlo/cli"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "kurlo": {
      "command": "npx",
      "args": [
        "-y",
        "@kurlo/cli"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "kurlo": {
      "command": "npx",
      "args": [
        "-y",
        "@kurlo/cli"
      ]
    }
  }
}

What it does

Run saved requests
Executes requests and returns responses with the app's engine.
Collection tests
Runs a collection's tests from the assistant.
Workspace writes
Adds requests, tests, examples and environment variables.
One-command install
Configures all detected AI clients at once.
Read-only mode
Installs only the tools that read and run.

Good for

  • Run an endpoint after changing code
  • Write tests from a real response
  • Add a request in the same commit as an endpoint
  • Share a Git-based workspace

Pricing

Open source

Free for teams of any size per the README

Prices change. Check kurlo.dev before you buy.

Kurlo FAQ

Is an account needed?

The site says no account is needed.

How does the assistant connect?

It starts kurlo mcp itself and talks over stdio.

Can I limit it?

Yes, --read-only installs only tools that read and run.

Where does it come from?

The @kurlo/cli npm package, via npx.

Is Kurlo free?

Yes. Kurlo is open source, so you can use and self-host it for free.

How do I add Kurlo to Claude Code?

Run this command in your terminal: claude mcp add kurlo -- npx -y @kurlo/cli

What are the best alternatives to Kurlo?

The closest alternatives to Kurlo are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Kurlo

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools